Search for exploits by CVE identifier
AI agents call search_by_cve to retrieve information from Exploit-DB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a lookup/search against a database to retrieve exploit information by CVE ID. It has no side effects - it only reads and returns data. While the results may contain sensitive security information useful for attacks, the tool itself is a passive data retrieval mechanism. The risk is informational rather than operational.
From the tool's definition Tool description states it 'Search[es] for exploits by CVE identifier' - a query operation that retrieves data from the Exploit-DB database.
Attacks that exploit this kind of access
Search for exploits by CVE identifier. It is categorised as a Read tool in the Exploit-DB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Exploit-DB MCP Server MCP server in PolicyLayer and add a rule for search_by_cve: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Exploit-DB MCP Server. Nothing to install.
search_by_cve is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_by_cve rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_by_cve. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_by_cve is provided by the Exploit-DB MCP Server MCP server (johnohhh1/exploitdb-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →